No abstract

Monitoring and describing the physical movements and body postures of animals is one of the most fundamental tasks of ethology. The more precise the observations are the more sophisticated the interpretations can be about the biology of a certain individual or species. Animal-borne data loggers have recently contributed much to the collection of motion-data from individuals, however, the problem of translating these measurements to distinct behavioural categories to create an ethogram is not overcome yet. The objective of the present study was to develop a “behaviour tracker”: a system composed of a multiple sensor data-logger device (with a tri-axial accelerometer and a tri-axial gyroscope) and a supervised learning algorithm as means of automated identification of the behaviour of freely moving dogs. We collected parallel sensor measurements and video recordings of each of our subjects (Belgian Malinois, N=12; Labrador Retrievers, N=12) that were guided through a predetermined series of standard activities. Seven behavioural categories (lay, sit, stand, walk, trot, gallop, canter) were pre-defined and each video recording was tagged accordingly. Evaluation of the measurements was performed by support vector machine (SVM) classification. During the analysis we used different combinations of independent measurements for training and validation (belonging to the same or different individuals or using different training data size) to determine the robustness of the application. We reached an overall accuracy of above 90% perfect identification of all the defined seven categories of behaviour when both training and validation data belonged to the same individual, and over 80% perfect recognition rate using a generalized training data set of multiple subjects. Our results indicate that the present method provides a good model for an easily applicable, fast, automatic behaviour classification system that can be trained with arbitrary motion patterns and potentially be applied to a wide range of species and situations.

No abstract

No abstract

The ultimate objective of this paper is to develop new techniques that can be used for the analysis of performance degradation due to statistical uncertainty for a wide class of linear stochastic systems. For this we need new technical tools similar to those used in [L. Gerencsér, Statist. Plann. Inference, 41 (1994), pp. 303-325]. The immediate technical objective is to extend the previous technical results to the Djereveckii-Fradkov-Ljung scheme with enforced boundedness. Our starting point is a standard approximation of the estimation error used in the asymptotic theory of recursive estimation. Tight control of the difference between the estimation error and its standard approximation, referred to as residuals, is a crucial point in our applications. The main technical advance of the present paper is a set of strong approximation theorems for three closely related recursive estimation algorithms in which, for any q ≥ 1, the Lq-norms of the residual terms are shown to tend to zero with rate N −1/2−ε with some ε > 0. This is a significant extension of previous results for the recursive prediction error or RPE estimator of ARMA processes given in [L. Gerencsér, Systems Control Lett., 21 (1993), pp. 347-351]. Two useful corollaries will be derived. In the first a standard transform of the estimation-error process for the basic recursive estimation method, Algorithm CR, will be shown to be L-mixing, while in the second the asymptotic covariance matrix of the estimator for the same method will be given. Applications to multivariable adaptive prediction and the minimum-variance self-tuning regulator for ARMAX systems will be described. Introduction.The ultimate objective of this paper is to develop new techniques for the analysis of performance degradation due to statistical uncertainty for a wide class of linear stochastic systems. Performance degradation due to statistical uncertainty, called regret, following [46], can be computed at a single time moment, yielding instantaneous regret, or it can be summed over time, yielding cumulative regret. The objective of the paper is to develop new techniques that can be used for analyzing the pathwise (almost sure) asymptotics of the cumulative regret for a class of adaptive prediction and stochastic adaptive control problems.A number of examples on the interaction of identification and control are available in the identification for control literature, see [29,40,41]. While those papers contain fundamentally new ideas, the analysis they present contains heuristic elements. In particular, they assume the independence of actually weakly dependent quantities in order to simplify the computation of the instantaneous regret. The present paper lays the foundations for a rigorous discussion of these heuristic arguments. Special examples of these new technical tools have been developed in the context of adaptive prediction of ARMA processes in [24].

Previous research proves dogs' outstanding success in socio-communicative interactions with humans; however, little is known about other domestic species' interspecific skills when kept as companion animals. Our aim was to assess highly socialized young miniature pigs' spontaneous reactions in interactions with humans in direct comparison with that of young family dogs. All subjects experienced similar amount of socialization in human families. In Study 1, we investigated the appearance of human-oriented behaviours without the presence of food (Control condition) when a previously provided food reward was withheld (Food condition). In Study 2, we measured responsiveness to two types of the distal pointing gesture (dynamic sustained and momentary) in a two-way object choice test. In the Control condition of Study 1, the duration of pigs' and dogs' orientation towards and their frequency of touching the human's body was similar. In the Food condition, these behaviours and orienting to the human's face were intensified in both species. However, pigs exhibited face-orientation to an overall lesser extent and almost exclusively in the Food condition. In Study 2, only dogs relied spontaneously on the distal dynamic-sustained pointing gesture, while all pigs developed side bias. The results suggest that individual familiarization to a human environment enables the spontaneous appearance of similar socio-communicative behaviours in dogs and pigs, however, species predispositions might cause differences in the display of specific signals as well as in the success of spontaneously responding to certain types of the human pointing gestures.

Automated monitoring of the movements and behaviour of animals is a valuable research tool. Recently, machine learning tools were applied to many species to classify units of behaviour. For the monitoring of wild species, collecting enough data for training models might be problematic, thus we examine how machine learning models trained on one species can be applied to another closely related species with similar behavioural conformation. We contrast two ways to calculate accuracies, termed here as overall and threshold accuracy, because the field has yet to define solid standards for reporting and measuring classification performances. We measure 21 dogs and 7 wolves, and find that overall accuracies are between 51 and 60% for classifying 8 behaviours (lay, sit, stand, walk, trot, run, eat, drink) when training and testing data are from the same species and between 41 and 51% when training and testing is cross-species. We show that using data from dogs to predict the behaviour of wolves is feasible. We also show that optimising the model for overall accuracy leads to similar overall and threshold accuracies, while optimizing for threshold accuracy leads to threshold accuracies well above 80%, but yielding very low overall accuracies, often below the chance level. Moreover, we show that the most common method for dividing the data between training and testing data (random selection of test data) overestimates the accuracy of models when applied to data of new specimens. Consequently, we argue that for the most common goals of animal behaviour recognition overall accuracy should be the preferred metric. Considering, that often the goal is to collect movement data without other methods of observation, we argue that training data and testing data should be divided by individual and not randomly.

Abstract-The sequence of recursive estimators for function minimization generated by Spall's simultaneous perturbation stochastic approximation (SPSA) method, presented in [25], combined with a suitable restarting mechanism is considered. It is proved that this sequence converges under certain conditions with rate O(n 0=2 ) for some >0, the best value being = 2=3, where the rate is measured by the Lq-norm of the estimation error for any 1 q < 1. The authors also present higher order SPSA methods. It is shown that the error exponent /2 can be arbitrarily close to 1/2 if the Hessian matrix of the cost function at the minimizing point has all its eigenvalues to the right of 1/2, the cost function is sufficiently smooth, and a sufficiently high-order approximation of the derivative is used.